Vehicle type recognition method with deep network model based on spatial pyramid pooling

Abstract

The invention discloses a vehicle type recognition method with a deep network model based on spatial pyramid pooling. The method comprises the steps that images in a vehicle type database are input into the deep network model for convolution layer characteristic extraction, so that a convolution layer characteristic diagram is constituted; spatial pyramid convolution computation is carried out to each image in the convolution layer characteristic diagram according to different scales, so that a characteristic diagram of spatial pyramid layers is constituted; all the characteristics of the spatial pyramid layers are pooled to constitute full-connected layers, so that a final characteristic representations of vehicle type images can be obtained; the characteristic representations off the vehicle type images are used in training of a linear support vector machine to obtain a vehicle type recognition system; and the characteristic representation of a to-be-recognized vehicle is also acquired and input into the recognition system, so that the vehicle type can be recognized. A traditional deep network model requires that an input image must have a fixed size, so that operations of large-scale vehicle type image data are limited. The method disclosed by the invention adopts the deep network model based on the spatial pyramid pooling, so that the problem is effectively solved; and the method has high practicability and robustness.

Description

technical field [0001] The invention belongs to the technical field of machine learning, pattern classification and recognition, and in particular relates to a car model recognition method based on a deep network model of spatial pyramid pooling. Background of the invention [0002] With the continuous improvement of living standards in modern society and the rapid growth of the number of cars, traffic supervision is facing great challenges. As an important means of traffic supervision, video surveillance system has been widely used in various fields of modern traffic. However, the traditional method of relying on manual interpretation can no longer meet the needs of today's massive traffic video processing, and it has become an inevitable trend to build an intelligent recognition system to automatically process various traffic video information. The identification of vehicle types in traffic video images, as a key technology in construction, has long been widely concerned ...

AI Technical Summary

Problems solved by technology

[0004] However, the size of the input image of the traditional convolutional neural network architecture is fixed (for example: 256x256), and this artificially changing the size of the input image destroys the scale and aspect ratio of the input image, so there are problems: (1 ) The choice of scale is subjective. For different targets, the most suitable size may be different; (2) For images of different sizes and aspect ratios, forcing the transformation to a fixed size will lose information; (3) The forced transformed image may not contain a complete image, and may also cause geometric deformation of the image

Images